Shaohang Wei
Results
2
repositories owned by
Shaohang Wei
24-Game-Reasoning
33
Stars
2
Forks
33
Watchers
超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1
TIME
27
Stars
0
Forks
27
Watchers
[NeurIPS 2025 D&B (Spotlight🌟)] TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenario